Dataset

Dataset: Dolphin, an open-source implementation of Microsoft's Orca

Private Dataset of gpt4/gpt3.5 dialogues in Chinese to increase its multilingual abilities.

Training

20 hours on 6 x A800s

Safetensors

Model size

7.24B params

Tensor type

FP16

Inference Examples

Inference API (serverless) is not available, repository is disabled.